A novel simple QSAR model for the prediction of anti-HIV activity using multiple linear regression analysis

Antreas Afantitis; Georgia Melagraki; Haralambos Sarimveis; Panayiotis A Koutentis; John Markopoulos; Olga Igglessi-Markopoulou

doi:10.1007/s11030-005-9012-2

A novel simple QSAR model for the prediction of anti-HIV activity using multiple linear regression analysis

Mol Divers. 2006 Aug;10(3):405-14. doi: 10.1007/s11030-005-9012-2. Epub 2006 Aug 1.

Authors

Antreas Afantitis¹, Georgia Melagraki, Haralambos Sarimveis, Panayiotis A Koutentis, John Markopoulos, Olga Igglessi-Markopoulou

Affiliation

¹ School of Chemical Engineering, National Technical University of Athens, Athens, Greece.

PMID: 16896545
DOI: 10.1007/s11030-005-9012-2

Abstract

A quantitative-structure activity relationship was obtained by applying Multiple Linear Regression Analysis to a series of 80 1-[2-hydroxyethoxy-methyl]-6-(phenylthio) thymine (HEPT) derivatives with significant anti-HIV activity. For the selection of the best among 37 different descriptors, the Elimination Selection Stepwise Regression Method (ES-SWR) was utilized. The resulting QSAR model (R (2) (CV) = 0.8160; S (PRESS) = 0.5680) proved to be very accurate both in training and predictive stages.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Anti-HIV Agents / chemistry*
Anti-HIV Agents / pharmacology*
HIV Reverse Transcriptase / antagonists & inhibitors
HIV-1 / drug effects*
Humans
Linear Models
Neural Networks, Computer
Quantitative Structure-Activity Relationship*
Reverse Transcriptase Inhibitors / chemistry
Reverse Transcriptase Inhibitors / pharmacology
Thymine / analogs & derivatives
Thymine / chemistry
Thymine / pharmacology

Substances

Anti-HIV Agents
Reverse Transcriptase Inhibitors
1-((2-hydroxyethoxy)methyl)-6-(phenylthio)thymine
HIV Reverse Transcriptase
Thymine